© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-CLT-HP
    7. 587
    Prev
    Next
    INDEX
    Explanations

    drinking and optimization

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ContentAsync
    -0.79
    PreferredItem
    -0.79
    ImageContext
    -0.77
    aarrggbb
    -0.68
    verwijspagina
    -0.67
    RUnlock
    -0.67
    Autoritní
    -0.67
     Италијани
    -0.67
     autorytatywna
    -0.67
    InitStruct
    -0.66
    POSITIVE LOGITS
    Étymologie
    0.49
    elance
    0.45
     offering
    0.45
     verksamhet
    0.43
    OPTIONS
    0.43
    cellona
    0.43
     offer
    0.42
    urlpatterns
    0.42
    cnx
    0.42
     deeply
    0.41
    Activations Density 0.009%

    No Known Activations